Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Legal jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    によ
    -0.06
    間に
    -0.06
    映
    -0.06
     školy
    -0.06
    리고
    -0.05
    λικά
    -0.05
     shelters
    -0.05
     rozsah
    -0.05
     уча
    -0.05
     shoulder
    -0.05
    POSITIVE LOGITS
     unve
    0.07
    _attr
    0.07
     Luckily
    0.07
    .rx
    0.07
     dumping
    0.07
    orizontal
    0.07
     holland
    0.07
     Nov
    0.07
     director
    0.07
    special
    0.06
    Act Density 0.004%

    No Known Activations